Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Canvas-LMS-MCP/canvas-teacher-mcp --skill grade-nbgit clone --depth 1 https://github.com/Canvas-LMS-MCP/canvas-teacher-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-nb)<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-nb"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-nb/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-nb"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-nb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00142 | $0.04538 |
| Opus 5.5 | $0.00057 | $0.01815 |
| Sonnet 5.5 | $0.00028 | $0.00908 |
| Haiku 4.5 | $0.00014 | $0.00454 |
Grade A, and why
grade-nb scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grade-nb — notebook + revision-history inspection (sub-skill of grade)
Invoked FROM skills/grade/SKILL.md when a submission IS (or is designated) a Colab/Jupyter notebook —
then it is REQUIRED, not optional (do not eyeball an NB on the bare general path). It runs INSIDE
the full grade spine — it does NOT replace or shortcut it:
Step 0 (scope: needs-grading queue + late/waivers) → Stage A (the ENGINE gathers via
attachments.read → graders/nb.py: notebook{cells, pinned revisions} + body/all_text, then
nb_inspect.resolve_tasks region completeness + revision_progression/score_revision process →
emitted as review_content) → Stage B (ALL general rules — §0Z FULL read, instructions rubric,
per-below-max reason, comment_render — the AI SCORES from review_content: comp per-problem 1/N,
rev process, refl from the reflection location) → report → self-challenge → POST. It supplies the
NB-specific DETAIL within Stage A + Stage B; it NEVER skips Step 0 or the general Stage-B rules. Policy
homes: GRADING.md Part C + GradingEngine/NbInspect.md (this file orders them into steps — it does
not re-decide policy).
⛔ Two rules that made past NB grading wrong (do NOT repeat)
- §0Z — never truncate. Read the WHOLE notebook, every cell source + output, IN FULL. The engine
lib/nb_inspect.load_notebookreads the entire file (raises if it can't) so nothing is sliced. - DIFF vs the template — never regex the merged notebook. Judge only the student-ADDED cells
(
template_added_cells(student, template)). The template's own example<img>, theplaceholder, and provided task cells will fool a merged scan.
Fetching = the ENGINE's job (grade-nb never calls gws)
attachments.read(submission) (called by graders/nb.py) fetches the notebook in ONE read →
["notebook"] = {drive_id, accessible, cells, revisions(pinned)} PLUS body_text / all_text
(where the Reflection lives). grade-nb / any grader NEVER calls gws directly (Attachments.md;
engine selftest greps for gws/HTTP outside attachments.py → STOP). The 2026-07-03 gws-cwd
detail lives INSIDE attachments.py, not here.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 227 lines · 142 tokens per session scan A fd101eb00f4b
grade-nb is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 142 tokens to every session and 4,538 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.